sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers");
BUG_ON(IS_ERR(sync_supers_tsk));
- init_timer(&sync_supers_timer);
setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0);
bdi_arm_supers_timer();
}
subsys_initcall(default_bdi_init);
-static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
-{
- memset(wb, 0, sizeof(*wb));
-
- wb->bdi = bdi;
- wb->last_old_flush = jiffies;
- INIT_LIST_HEAD(&wb->b_dirty);
- INIT_LIST_HEAD(&wb->b_io);
- INIT_LIST_HEAD(&wb->b_more_io);
-}
-
int bdi_has_dirty_io(struct backing_dev_info *bdi)
{
return wb_has_dirty_io(&bdi->wb);
bdi_arm_supers_timer();
}
+static void wakeup_timer_fn(unsigned long data)
+{
+ struct backing_dev_info *bdi = (struct backing_dev_info *)data;
+
+ spin_lock_bh(&bdi->wb_lock);
+ if (bdi->wb.task) {
+ trace_writeback_wake_thread(bdi);
+ wake_up_process(bdi->wb.task);
+ } else {
+ /*
+ * When bdi tasks are inactive for long time, they are killed.
+ * In this case we have to wake-up the forker thread which
+ * should create and run the bdi thread.
+ */
+ trace_writeback_wake_forker_thread(bdi);
+ wake_up_process(default_backing_dev_info.wb.task);
+ }
+ spin_unlock_bh(&bdi->wb_lock);
+}
+
+/*
+ * This function is used when the first inode for this bdi is marked dirty. It
+ * wakes-up the corresponding bdi thread which should then take care of the
+ * periodic background write-out of dirty inodes. Since the write-out would
+ * starts only 'dirty_writeback_interval' centisecs from now anyway, we just
+ * set up a timer which wakes the bdi thread up later.
+ *
+ * Note, we wouldn't bother setting up the timer, but this function is on the
+ * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
+ * by delaying the wake-up.
+ */
+void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
+{
+ unsigned long timeout;
+
+ timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
+ mod_timer(&bdi->wb.wakeup_timer, jiffies + timeout);
+}
+
+/*
+ * Calculate the longest interval (jiffies) bdi threads are allowed to be
+ * inactive.
+ */
+static unsigned long bdi_longest_inactive(void)
+{
+ unsigned long interval;
+
+ interval = msecs_to_jiffies(dirty_writeback_interval * 10);
+ return max(5UL * 60 * HZ, interval);
+}
+
static int bdi_forker_thread(void *ptr)
{
struct bdi_writeback *me = ptr;
set_user_nice(current, 0);
for (;;) {
- struct task_struct *task;
+ struct task_struct *task = NULL;
struct backing_dev_info *bdi;
enum {
NO_ACTION, /* Nothing to do */
FORK_THREAD, /* Fork bdi thread */
+ KILL_THREAD, /* Kill inactive bdi thread */
} action = NO_ACTION;
/*
* Temporary measure, we want to make sure we don't see
* dirty data on the default backing_dev_info
*/
- if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list))
+ if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) {
+ del_timer(&me->wakeup_timer);
wb_do_writeback(me, 0);
+ }
spin_lock_bh(&bdi_lock);
set_current_state(TASK_INTERRUPTIBLE);
- /*
- * Check if any existing bdi's have dirty data without
- * a thread registered. If so, set that up.
- */
list_for_each_entry(bdi, &bdi_list, bdi_list) {
bool have_dirty_io;
action = FORK_THREAD;
break;
}
+
+ spin_lock(&bdi->wb_lock);
+
+ /*
+ * If there is no work to do and the bdi thread was
+ * inactive long enough - kill it. The wb_lock is taken
+ * to make sure no-one adds more work to this bdi and
+ * wakes the bdi thread up.
+ */
+ if (bdi->wb.task && !have_dirty_io &&
+ time_after(jiffies, bdi->wb.last_active +
+ bdi_longest_inactive())) {
+ task = bdi->wb.task;
+ bdi->wb.task = NULL;
+ spin_unlock(&bdi->wb_lock);
+ set_bit(BDI_pending, &bdi->state);
+ action = KILL_THREAD;
+ break;
+ }
+ spin_unlock(&bdi->wb_lock);
}
spin_unlock_bh(&bdi_lock);
* the bdi from the thread.
*/
bdi_flush_io(bdi);
- } else
+ } else {
+ /*
+ * The spinlock makes sure we do not lose
+ * wake-ups when racing with 'bdi_queue_work()'.
+ */
+ spin_lock_bh(&bdi->wb_lock);
bdi->wb.task = task;
+ spin_unlock_bh(&bdi->wb_lock);
+ }
+ break;
+
+ case KILL_THREAD:
+ __set_current_state(TASK_RUNNING);
+ kthread_stop(task);
break;
case NO_ACTION:
- if (dirty_writeback_interval)
- schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
+ if (!wb_has_dirty_io(me) || !dirty_writeback_interval)
+ /*
+ * There are no dirty data. The only thing we
+ * should now care about is checking for
+ * inactive bdi threads and killing them. Thus,
+ * let's sleep for longer time, save energy and
+ * be friendly for battery-driven devices.
+ */
+ schedule_timeout(bdi_longest_inactive());
else
- schedule();
+ schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
try_to_freeze();
/* Back to the main loop */
continue;
}
+
+ /*
+ * Clear pending bit and wakeup anybody waiting to tear us down.
+ */
+ clear_bit(BDI_pending, &bdi->state);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&bdi->state, BDI_pending);
}
return 0;
const char *fmt, ...)
{
va_list args;
- int ret = 0;
struct device *dev;
if (bdi->dev) /* The driver needs to use separate queues per device */
- goto exit;
+ return 0;
va_start(args, fmt);
dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args);
va_end(args);
- if (IS_ERR(dev)) {
- ret = PTR_ERR(dev);
- goto exit;
- }
-
- spin_lock_bh(&bdi_lock);
- list_add_tail_rcu(&bdi->bdi_list, &bdi_list);
- spin_unlock_bh(&bdi_lock);
+ if (IS_ERR(dev))
+ return PTR_ERR(dev);
bdi->dev = dev;
wb->task = kthread_run(bdi_forker_thread, wb, "bdi-%s",
dev_name(dev));
- if (IS_ERR(wb->task)) {
- wb->task = NULL;
- ret = -ENOMEM;
-
- bdi_remove_from_list(bdi);
- goto exit;
- }
+ if (IS_ERR(wb->task))
+ return PTR_ERR(wb->task);
}
bdi_debug_register(bdi, dev_name(dev));
set_bit(BDI_registered, &bdi->state);
+
+ spin_lock_bh(&bdi_lock);
+ list_add_tail_rcu(&bdi->bdi_list, &bdi_list);
+ spin_unlock_bh(&bdi_lock);
+
trace_writeback_bdi_register(bdi);
-exit:
- return ret;
+ return 0;
}
EXPORT_SYMBOL(bdi_register);
return;
/*
- * If setup is pending, wait for that to complete first
+ * Make sure nobody finds us on the bdi_list anymore
*/
- wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
- TASK_UNINTERRUPTIBLE);
+ bdi_remove_from_list(bdi);
/*
- * Make sure nobody finds us on the bdi_list anymore
+ * If setup is pending, wait for that to complete first
*/
- bdi_remove_from_list(bdi);
+ wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
+ TASK_UNINTERRUPTIBLE);
/*
* Finally, kill the kernel thread. We don't need to be RCU
if (bdi->dev) {
trace_writeback_bdi_unregister(bdi);
bdi_prune_sb(bdi);
+ del_timer_sync(&bdi->wb.wakeup_timer);
if (!bdi_cap_flush_forker(bdi))
bdi_wb_shutdown(bdi);
}
EXPORT_SYMBOL(bdi_unregister);
+static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+{
+ memset(wb, 0, sizeof(*wb));
+
+ wb->bdi = bdi;
+ wb->last_old_flush = jiffies;
+ INIT_LIST_HEAD(&wb->b_dirty);
+ INIT_LIST_HEAD(&wb->b_io);
+ INIT_LIST_HEAD(&wb->b_more_io);
+ setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi);
+}
+
int bdi_init(struct backing_dev_info *bdi)
{
int i, err;